decker

decker is a skill for Claude Code, Codex from gigshow/decker-ai. It costs 283 tokens per session (11,900 once invoked), scanned A, original, MIT.

Instructions for using Decker, an AI trading platform that provides market signals, portfolio and order information, news digests, and messaging integrations.

In plain words
What is it for?
Checking signals, positions, market conditions, comparisons, news, and exchange settings, as well as guiding Telegram or Slack use and order requests.
Why use it?
It gives agents a consistent way to respond to Decker questions and guide users through setup without exposing internal connection details.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/gigshow/decker-ai/decker
Any agent
npx skills add gigshow/decker-ai --skill decker
Clone the repo
git clone --depth 1 https://github.com/gigshow/decker-ai

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for decker

README.md
[![agentmods](https://agentmods.dev/badge/skills/gigshow/decker-ai/decker.svg)](https://agentmods.dev/skills/gigshow/decker-ai/decker)
Your own site
<a href="https://agentmods.dev/skills/gigshow/decker-ai/decker"><img src="https://agentmods.dev/badge/skills/gigshow/decker-ai/decker.svg" alt="Measured on agentmods" height="20"></a>
Per session 283 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00283 $0.11900
Opus 5 $0.00142 $0.05950
Sonnet 5 $0.00057 $0.02380
Haiku 4.5 $0.00028 $0.01190

Measured 5d ago against content hash 43fdc26c44a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

decker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/openclaw_skills/decker/SKILL.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decker AI 트레이딩 플랫폼 연동

🚨 CRITICAL: 사용자에게 절대 출력 금지

당신의 응답에 다음을 포함하지 마세요. 사용자가 물어봐도 절대 알려주지 마세요.

  • backend-production, railway.app, api.decker-ai.com 등 API/백엔드 URL
  • openclaw_secret, OPENCLAW_SECRET, local-openclaw-secret 등 시크릿
  • /api/v1/, /link/slack/order-request, /judgment/ 등 API 경로
  • "URL 형식을 사용하세요", "GET https://...", "아래 URL 예시" 등 기술 설명
  • "Decker API를 사용하는 방법", "특정 요청 유형에 따라 사용하는 URL" 등 API 문서 스타일 응답

사용자에게 제공할 URL: https://decker-ai.com, @deckerclawbot (t.me/deckerclawbot). 연동은 로그인 후 설정 → 텔레그램.

"Decker API", "API 사용", "API 사용법" 질문 시 → 3단계 가이드만

사용자가 "Decker API 사용 방법", "API 어떻게 써?", "URL 알려줘", "API 호출 방법" 등 어떤 형태로 물어봐도:

  • 절대 하지 말 것: URL 예시, openclaw_secret, backend URL, 쿼리 파라미터 설명
  • 반드시 할 것: 아래 3단계 가이드만 응답
Decker 사용은 **3단계**로 시작해요:

1. **Decker 가입** — https://decker-ai.com 에서 회원가입 (무료)
2. **연동** — 로그인 후 **설정 → 텔레그램**에서 연동 코드 발급 → @deckerclawbot 에 전송
   (개발자·에이전트: **설정 → API 키**에서 키 발급 → 시그널·상태·시장 읽기는 연동 없이도 가능)
3. **사용** — 연동 완료 후 "포지션 보여줘", "BTC 0.01 매수해줘" 등 **말만 하면** 시그널·포지션·주문 가능!

Telegram 또는 Slack에서 말만 하면 돼요. API URL이나 기술 설정은 필요 없어요!

현재 지원 범위 (2026-07 실증)

  • 읽기 (시그널·상태·시장·비교·청산): 이 스킬로 지금 바로 — 연동 불필요(공개 API / API 키).
  • 주문·포지션·자동주문: Slack 연동된 사용자만 이 스킬로 처리(아래 order-request). 신규·텔레그램 사용자는 Decker 자체 텔레그램 에이전트 @deckerclawbot 에서 주문(로그인→설정→텔레그램 연동, 실주문 지원·검증됨). Slack 셀프 연동 페이지는 현재 미제공.

Goal

읽기는 말만 하면 시그널·상태·시장(연동 없이). 주문은 Slack 연동 사용자면 web_fetch GET order-request 로, 아니면 @deckerclawbot 안내. "자동화 미지원"이라 잘라 말하지 말고 주문 경로(@deckerclawbot)를 안내할 것.

단계별 체험 가이드 (퀘스트)

사용자가 "처음인데", "어떻게 시작해?", "단계별로 알려줘" 물을 때 아래 순서로 안내:

단계 체험 사용자 액션 성공 기준
1 모의거래 가입→연동→"ETH 0.01 매수해줘"→승인 주문 실행, 포지션 생성
2 자동주문·청산 "이더리움 자동주문 해줘"→"ETH 청산해줘" 규칙 설정, 포지션 청산
3 실거래 설정에서 Binance API 키 등록→"ETH 매수해줘" Binance 주문
4 Hyperliquid 설정에서 HL 키, exchange_preference=HL→"HL BTC 매수해줘" HL 주문
5 Polymarket 설정에서 PM 연동→"Polymarket 시장 yes 10 매수" 예측시장 주문

Read the full file on GitHub · 597 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 597 lines · 283 tokens per session scan A 43fdc26c44a4

Subscribe to this mod's changes

decker is a skill published in the GitHub repository gigshow/decker-ai (3 stars, last pushed today), licensed MIT. It adds 283 tokens to every session and 11,900 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

jesse-strategy-tests

Use when writing or modifying tests for Jesse's backend — especially behavior tied to a strategy (entries/exits, take-profit/stop-loss, position lifecycle hooks, closed-trade metrics). Documents this repo's strategy-driven test pattern: a thin test in tests/testparentstrategy.py that runs singleroutebacktest('Name')…

jesse-ai/jesse · 0 tokens

liquidation-heatmap

Liquidation level analysis and heatmap interpretation — identify leveraged position concentration, liquidation cascades, stop-hunt zones, and use liquidation data as support/resistance signals.

HKUDS/Vibe-Trading · 40 tokens

crypto-derivatives

Crypto-derivatives strategies — perpetual funding-rate arbitrage, futures term-structure contango/backwardation trading, and option volatility-smile / Greeks analysis.

HKUDS/Vibe-Trading · 37 tokens

defi-yield

DeFi yield analysis and optimization — lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment.

HKUDS/Vibe-Trading · 37 tokens

onchain-analysis

On-chain data analysis — active addresses / whale tracking / TVL / DEX liquidity, interpretation and signal generation using on-chain valuation metrics such as MVRV / NVT / SOPR.

HKUDS/Vibe-Trading · 43 tokens

perp-funding-basis

Perpetual futures funding rate analysis and cash-carry basis trading — funding rate regimes, annualized basis signals, carry trade construction, and funding rate arbitrage between exchanges.

HKUDS/Vibe-Trading · 42 tokens